cls_bpf.c 8.1 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158
/*
 * Berkeley Packet Filter based traffic classifier
 *
 * Might be used to classify traffic through flexible, user-defined and
 * possibly JIT-ed BPF filters for traffic control as an alternative to
 * ematches.
 *
 * (C) 2013 Daniel Borkmann <dborkman@redhat.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#include <linux/module.h>
#include <linux/types.h>
#include <linux/skbuff.h>
#include <linux/filter.h>
#include <net/rtnetlink.h>
#include <net/pkt_cls.h>
#include <net/sock.h>

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>");
MODULE_DESCRIPTION("TC BPF based classifier");

struct cls_bpf_head {
	struct list_head plist;
	u32 hgen;
};

struct cls_bpf_prog {
	struct sk_filter *filter;
	struct sock_filter *bpf_ops;
	struct tcf_exts exts;
	struct tcf_result res;
	struct list_head link;
	u32 handle;
	u16 bpf_len;
};

static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = {
	[TCA_BPF_CLASSID]	= { .type = NLA_U32 },
	[TCA_BPF_OPS_LEN]	= { .type = NLA_U16 },
	[TCA_BPF_OPS]		= { .type = NLA_BINARY,
				    .len = sizeof(struct sock_filter) * BPF_MAXINSNS },
};

static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
			    struct tcf_result *res)
{
	struct cls_bpf_head *head = tp->root;
	struct cls_bpf_prog *prog;
	int ret;

	list_for_each_entry(prog, &head->plist, link) {
		int filter_res = SK_RUN_FILTER(prog->filter, skb);

		if (filter_res == 0)
			continue;

		*res = prog->res;
		if (filter_res != -1)
			res->classid = filter_res;

		ret = tcf_exts_exec(skb, &prog->exts, res);
		if (ret < 0)
			continue;

		return ret;
	}

	return -1;
}

static int cls_bpf_init(struct tcf_proto *tp)
{
	struct cls_bpf_head *head;

	head = kzalloc(sizeof(*head), GFP_KERNEL);
	if (head == NULL)
		return -ENOBUFS;

	INIT_LIST_HEAD(&head->plist);
	tp->root = head;

	return 0;
}

static void cls_bpf_delete_prog(struct tcf_proto *tp, struct cls_bpf_prog *prog)
{
	tcf_unbind_filter(tp, &prog->res);
	tcf_exts_destroy(tp, &prog->exts);

	sk_unattached_filter_destroy(prog->filter);

	kfree(prog->bpf_ops);
	kfree(prog);
}

static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg)
{
	struct cls_bpf_head *head = tp->root;
	struct cls_bpf_prog *prog, *todel = (struct cls_bpf_prog *) arg;

	list_for_each_entry(prog, &head->plist, link) {
		if (prog == todel) {
			tcf_tree_lock(tp);
			list_del(&prog->link);
			tcf_tree_unlock(tp);

			cls_bpf_delete_prog(tp, prog);
			return 0;
		}
	}

	return -ENOENT;
}

static void cls_bpf_destroy(struct tcf_proto *tp)
{
	struct cls_bpf_head *head = tp->root;
	struct cls_bpf_prog *prog, *tmp;

	list_for_each_entry_safe(prog, tmp, &head->plist, link) {
		list_del(&prog->link);
		cls_bpf_delete_prog(tp, prog);
	}

	kfree(head);
}

static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle)
{
	struct cls_bpf_head *head = tp->root;
	struct cls_bpf_prog *prog;
	unsigned long ret = 0UL;

	if (head == NULL)
		return 0UL;

	list_for_each_entry(prog, &head->plist, link) {
		if (prog->handle == handle) {
			ret = (unsigned long) prog;
			break;
		}
	}

	return ret;
}

static void cls_bpf_put(struct tcf_proto *tp, unsigned long f)
{
}

static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
				   struct cls_bpf_prog *prog,
				   unsigned long base, struct nlattr **tb,
159
				   struct nlattr *est, bool ovr)
160 161 162
{
	struct sock_filter *bpf_ops, *bpf_old;
	struct tcf_exts exts;
163
	struct sock_fprog_kern tmp;
164 165 166 167 168 169 170 171
	struct sk_filter *fp, *fp_old;
	u16 bpf_size, bpf_len;
	u32 classid;
	int ret;

	if (!tb[TCA_BPF_OPS_LEN] || !tb[TCA_BPF_OPS] || !tb[TCA_BPF_CLASSID])
		return -EINVAL;

172
	tcf_exts_init(&exts, TCA_BPF_ACT, TCA_BPF_POLICE);
173
	ret = tcf_exts_validate(net, tp, tb, est, &exts, ovr);
174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193
	if (ret < 0)
		return ret;

	classid = nla_get_u32(tb[TCA_BPF_CLASSID]);
	bpf_len = nla_get_u16(tb[TCA_BPF_OPS_LEN]);
	if (bpf_len > BPF_MAXINSNS || bpf_len == 0) {
		ret = -EINVAL;
		goto errout;
	}

	bpf_size = bpf_len * sizeof(*bpf_ops);
	bpf_ops = kzalloc(bpf_size, GFP_KERNEL);
	if (bpf_ops == NULL) {
		ret = -ENOMEM;
		goto errout;
	}

	memcpy(bpf_ops, nla_data(tb[TCA_BPF_OPS]), bpf_size);

	tmp.len = bpf_len;
194
	tmp.filter = bpf_ops;
195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244

	ret = sk_unattached_filter_create(&fp, &tmp);
	if (ret)
		goto errout_free;

	tcf_tree_lock(tp);
	fp_old = prog->filter;
	bpf_old = prog->bpf_ops;

	prog->bpf_len = bpf_len;
	prog->bpf_ops = bpf_ops;
	prog->filter = fp;
	prog->res.classid = classid;
	tcf_tree_unlock(tp);

	tcf_bind_filter(tp, &prog->res, base);
	tcf_exts_change(tp, &prog->exts, &exts);

	if (fp_old)
		sk_unattached_filter_destroy(fp_old);
	if (bpf_old)
		kfree(bpf_old);

	return 0;

errout_free:
	kfree(bpf_ops);
errout:
	tcf_exts_destroy(tp, &exts);
	return ret;
}

static u32 cls_bpf_grab_new_handle(struct tcf_proto *tp,
				   struct cls_bpf_head *head)
{
	unsigned int i = 0x80000000;

	do {
		if (++head->hgen == 0x7FFFFFFF)
			head->hgen = 1;
	} while (--i > 0 && cls_bpf_get(tp, head->hgen));
	if (i == 0)
		pr_err("Insufficient number of handles\n");

	return i;
}

static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
			  struct tcf_proto *tp, unsigned long base,
			  u32 handle, struct nlattr **tca,
245
			  unsigned long *arg, bool ovr)
246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262
{
	struct cls_bpf_head *head = tp->root;
	struct cls_bpf_prog *prog = (struct cls_bpf_prog *) *arg;
	struct nlattr *tb[TCA_BPF_MAX + 1];
	int ret;

	if (tca[TCA_OPTIONS] == NULL)
		return -EINVAL;

	ret = nla_parse_nested(tb, TCA_BPF_MAX, tca[TCA_OPTIONS], bpf_policy);
	if (ret < 0)
		return ret;

	if (prog != NULL) {
		if (handle && prog->handle != handle)
			return -EINVAL;
		return cls_bpf_modify_existing(net, tp, prog, base, tb,
263
					       tca[TCA_RATE], ovr);
264 265 266 267 268 269
	}

	prog = kzalloc(sizeof(*prog), GFP_KERNEL);
	if (prog == NULL)
		return -ENOBUFS;

270
	tcf_exts_init(&prog->exts, TCA_BPF_ACT, TCA_BPF_POLICE);
271 272 273 274 275 276 277 278 279
	if (handle == 0)
		prog->handle = cls_bpf_grab_new_handle(tp, head);
	else
		prog->handle = handle;
	if (prog->handle == 0) {
		ret = -EINVAL;
		goto errout;
	}

280
	ret = cls_bpf_modify_existing(net, tp, prog, base, tb, tca[TCA_RATE], ovr);
281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297
	if (ret < 0)
		goto errout;

	tcf_tree_lock(tp);
	list_add(&prog->link, &head->plist);
	tcf_tree_unlock(tp);

	*arg = (unsigned long) prog;

	return 0;
errout:
	if (*arg == 0UL && prog)
		kfree(prog);

	return ret;
}

298
static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322
			struct sk_buff *skb, struct tcmsg *tm)
{
	struct cls_bpf_prog *prog = (struct cls_bpf_prog *) fh;
	struct nlattr *nest, *nla;

	if (prog == NULL)
		return skb->len;

	tm->tcm_handle = prog->handle;

	nest = nla_nest_start(skb, TCA_OPTIONS);
	if (nest == NULL)
		goto nla_put_failure;

	if (nla_put_u32(skb, TCA_BPF_CLASSID, prog->res.classid))
		goto nla_put_failure;
	if (nla_put_u16(skb, TCA_BPF_OPS_LEN, prog->bpf_len))
		goto nla_put_failure;

	nla = nla_reserve(skb, TCA_BPF_OPS, prog->bpf_len *
			  sizeof(struct sock_filter));
	if (nla == NULL)
		goto nla_put_failure;

323
	memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla));
324

325
	if (tcf_exts_dump(skb, &prog->exts) < 0)
326 327 328 329
		goto nla_put_failure;

	nla_nest_end(skb, nest);

330
	if (tcf_exts_dump_stats(skb, &prog->exts) < 0)
331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382
		goto nla_put_failure;

	return skb->len;

nla_put_failure:
	nla_nest_cancel(skb, nest);
	return -1;
}

static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg)
{
	struct cls_bpf_head *head = tp->root;
	struct cls_bpf_prog *prog;

	list_for_each_entry(prog, &head->plist, link) {
		if (arg->count < arg->skip)
			goto skip;
		if (arg->fn(tp, (unsigned long) prog, arg) < 0) {
			arg->stop = 1;
			break;
		}
skip:
		arg->count++;
	}
}

static struct tcf_proto_ops cls_bpf_ops __read_mostly = {
	.kind		=	"bpf",
	.owner		=	THIS_MODULE,
	.classify	=	cls_bpf_classify,
	.init		=	cls_bpf_init,
	.destroy	=	cls_bpf_destroy,
	.get		=	cls_bpf_get,
	.put		=	cls_bpf_put,
	.change		=	cls_bpf_change,
	.delete		=	cls_bpf_delete,
	.walk		=	cls_bpf_walk,
	.dump		=	cls_bpf_dump,
};

static int __init cls_bpf_init_mod(void)
{
	return register_tcf_proto_ops(&cls_bpf_ops);
}

static void __exit cls_bpf_exit_mod(void)
{
	unregister_tcf_proto_ops(&cls_bpf_ops);
}

module_init(cls_bpf_init_mod);
module_exit(cls_bpf_exit_mod);